Data-driven solar forecasting enables near-optimal economic decisions
Abstract
Solar energy adoption is critical to achieving net-zero emissions. However, it remains difficult for many industrial and commercial actors to decide on whether they should adopt distributed solar-battery systems, which is largely due to the unavailability of fast, low-cost, and high-resolution irradiance forecasts. Here, we present SunCastNet, a lightweight data-driven forecasting system that provides 0.05, 10-minute resolution predictions of surface solar radiation downwards (SSRD) up to 7 days ahead. SunCastNet, coupled with reinforcement learning (RL) for battery scheduling, reduces operational regret by 76--93\% compared to robust decision making (RDM). In 25-year investment backtests, it enables up to five of ten high-emitting industrial sectors per region to cross the commercial viability threshold of 12\% Internal Rate of Return (IRR). These results show that high-resolution, long-horizon solar forecasts can directly translate into measurable economic gains, supporting near-optimal energy operations and accelerating renewable deployment.
Keywords
Cite
@article{arxiv.2509.06925,
title = {Data-driven solar forecasting enables near-optimal economic decisions},
author = {Zhixiang Dai and Minghao Yin and Xuanhong Chen and Alberto Carpentieri and Jussi Leinonen and Boris Bonev and Chengzhe Zhong and Thorsten Kurth and Jingan Sun and Ram Cherukuri and Yuzhou Zhang and Ruihua Zhang and Farah Hariri and Xiaodong Ding and Chuanxiang Zhu and Dake Zhang and Yaodan Cui and Yuxi Lu and Yue Song and Bin He and Jie Chen and Yixin Zhu and Chenheng Xu and Maofeng Liu and Zeyi Niu and Wanpeng Qi and Xu Shan and Siyuan Xian and Ning Lin and Kairui Feng},
journal= {arXiv preprint arXiv:2509.06925},
year = {2025}
}
Comments
Main text ~12 pages, 4 figures, 0 tables